My SGLang got no response and keep using the GPUs #3945
Unanswered
someone132s
asked this question in
Q&A
Replies: 1 comment
-
|
solved by adding parameter --disable-radix-cache, but why? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I'm fresh here and I deployed a SGLang with model "DeepSeek R1 distill qwen2.5 32b q4" with docker-compose. I saw the server started, and ready to accept requests. I can also see theres logs indicating that the servers recieves the post request. However, it just keep running for a long time without any resposes.
Beta Was this translation helpful? Give feedback.
All reactions